Building text features for object image classification
Authors:
- 1 June 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1367-1374
Abstract
We introduce a text-based image feature and demonstrate that it consistently improves performance on hard object classification problems. The feature is built using an auxiliary dataset of images annotated with tags, downloaded from the Internet. We do not inspect or correct the tags and expect that they are noisy. We obtain the text feature of an unannotated image from the tags of its k-nearest neighbors in this auxiliary collection. A visual classifier presented with an object viewed under novel circumstances (say, a new viewing direction) must rely on its visual examples. Our text feature may not change, because the auxiliary dataset likely contains a similar picture. While the tags associated with images are noisy, they are more stable when appearance changes. We test the performance of this feature using PASCAL VOC 2006 and 2007 datasets. Our feature performs well, consistently improves the performance of visual object classifiers, and is particularly effective when the training dataset is small.Keywords
This publication has 10 references indexed in Scilit:
- IM2GPS: estimating geographic information from a single image2008
- Filtering Internet image search results towards keyword based category recognition2008
- Scene completion using millions of photographs2007
- Learning Visual Representations using Images with Captions2007
- OPTIMOL: automatic Online Picture collecTion via Incremental MOdel Learning2007
- Harvesting Image Databases from the Web2007
- A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition2005
- Names and faces in the news2004
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001